Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add OneWave-AI/open-agent-stack --skill pipeline-reviewgit clone --depth 1 https://github.com/OneWave-AI/open-agent-stackWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/onewave-ai/open-agent-stack/pipeline-review)<a href="https://agentmods.dev/skills/onewave-ai/open-agent-stack/pipeline-review"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/pipeline-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/onewave-ai/open-agent-stack/pipeline-review"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/pipeline-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.00435 |
| Opus 5 | $0.00020 | $0.00217 |
| Sonnet 5 | $0.00008 | $0.00087 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
pipeline-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Pipeline Review
A pipeline review answers three questions per deal: is it real, is it moving, and what happens next. Input: CRM pipeline (via connected MCP) or a pasted/exported deal list with stages, amounts, and last-activity dates.
Workflow
- Staleness sweep. Flag every deal with no activity beyond its stage's normal rhythm (default: 14 days early-stage, 7 days late-stage). Sort by amount -- the biggest quiet deal is the headline.
- Next-action audit. Every open deal gets exactly one named next action with an owner and a date. Deals where the next action is "waiting on them" get a nudge drafted; deals where nobody can name a next action get flagged as not-real candidates.
- Honest forecast. Split the pipeline: commit (verbal yes or contract out), probable (champion engaged, process defined), possible (interest without process), and hope (everything else). Report the gap between quota and commit+probable -- that gap is the week's real to-do list.
- The kill list. Deals stalled past two cycles with no champion and no process: recommend closing them out. A pipeline padded with dead deals hides the real gap until it is too late to fix.
- Output. One-page review: headline risks, the stalled list with unstick moves per deal, the forecast split, and the five actions that most change this quarter's number.
Rules
- Last-activity date is the truth serum -- what the rep says about a deal matters less than when the buyer last did anything.
- "Hope" is a category, not an insult; it just does not forecast.
- Every recommendation is an action with a name on it, not an observation.
- Track review over review: deals that were stalled last week and are stalled this week escalate automatically.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 24 lines · 40 tokens per session scan A 2f28c4421d5c
pipeline-review is a skill published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 28d ago), licensed MIT. It adds 40 tokens to every session and 435 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
comps-analysis
Build comparable-company valuation workbooks in Excel.
ascii-video
ASCII video: convert video/audio to colored ASCII MP4/GIF.
pretext
Build creative browser demos with DOM-free text layout.
pinggy-tunnel
Zero-install localhost tunnels over SSH via Pinggy.
weights-and-biases
W&B: log ML experiments, sweeps, model registry, dashboards.
grounded-citations
Ground answers and documents in cited, verifiable sources.